Method of controlling autonomous vehicle, electronic device, and storage medium

Patent metadata

Field	Value
Publication number	US-12509065-B2
Application number	US-202318199525-A
Country	US
Kind code	B2
Filing date	May 19, 2023
Priority date	May 20, 2022
Publication date	Dec 30, 2025
Grant date	Dec 30, 2025

Abstract

A method of controlling an autonomous vehicle, an electronic device, and a storage medium, which relate to fields of an artificial intelligence, autonomous driving, intelligent transportation, high-definition maps, cloud services, and Internet of Vehicles technologies. The method includes determining, in response to an obstacle avoidance instruction being received, an obstacle avoidance strategy in lane changing according to first obstacle data of a target obstacle, the obstacle avoidance instruction being generated in response to determining that a first relationship between the target obstacle and a vehicle meets a predetermined collision condition, and the first relationship being generated based on the first obstacle data and first vehicle data of the vehicle; controlling the vehicle to travel according to the obstacle avoidance strategy; and updating a planned path for lane changing in response to a risk relief instruction being received, so that the vehicle travels according to the updated planned path.

First claim

What is claimed is:

1 . A method of controlling an autonomous vehicle, comprising:
acquiring scene data for lane changing about surroundings of a vehicle in response to a lane-changing instruction being received; determining a lane-changing entrance based on the scene data for lane changing; generating a planned path for lane changing based on a travelling location of the vehicle and the lane-changing entrance; determining, in response to an obstacle avoidance instruction being received, an obstacle avoidance strategy in lane changing according to first obstacle data of a target obstacle in a process of controlling the vehicle to change lanes according to the planned path for lane changing, wherein the obstacle avoidance instruction is generated in response to determining that a first relationship between the target obstacle and the vehicle meets a predetermined collision condition, the first relationship between the target obstacle and the vehicle is generated based on the first obstacle data of the target obstacle and first vehicle data of the vehicle, and the obstacle avoidance strategy in lane changing refers to changing a travelling state of the vehicle while maintaining a lane change; controlling the vehicle to travel according to the obstacle avoidance strategy in lane changing; and updating a planned path for lane changing in response to a risk relief instruction being received, so that the vehicle travels according to the updated planned path for lane changing, wherein the risk relief instruction is generated in response to determining that a second relationship between the target obstacle and the vehicle does not meet the predetermined collision condition, and the second relationship between the target obstacle and the vehicle is generated based on second obstacle data of the target obstacle and second vehicle data of the vehicle.

2 . The method according to claim 1 , wherein the updating a planned path for lane changing in response to a risk relief instruction being received comprises:
determining current scene data for lane changing in response to the risk relief instruction being received, wherein the current scene data for lane changing comprises at least one of obstacle data related to lane changing, vehicle data, environmental data, or road traffic rule data; and updating the planned path for lane changing based on the current scene data for lane changing.

3 . The method according to claim 1 , further comprising: before the updating a planned path for lane changing in response to a risk relief instruction being received, acquiring the second obstacle data of the target obstacle and the second vehicle data of the vehicle;
determining the second relationship between the target obstacle and the vehicle based on the second obstacle data of the target obstacle and the second vehicle data of the vehicle; and generating the risk relief instruction in response to determining that the second relationship between the target obstacle and the vehicle does not meet the predetermined collision condition.

4 . The method according to claim 3 , wherein the determining the second relationship between the target obstacle and the vehicle based on the second obstacle data of the target obstacle and the second vehicle data of the vehicle comprises:
determining a current category result of lane changing based on the current scene data for lane changing; determining an interaction data category based on the current category result of lane changing; determining, from the second obstacle data, target obstacle data matched with the interaction data category; determining, from the second vehicle data, target vehicle data matched with the interaction data category; and determining the second relationship between the target obstacle and the vehicle, based on the target obstacle data of the target obstacle and the target vehicle data of the vehicle.

5 . The method according to claim 1 , further comprising:
determining a number of jump instructions received within a predetermined time period, wherein the jump instruction comprises the obstacle avoidance instruction and/or the risk relief instruction, wherein the number of jump instructions includes one of a first number of received obstacle avoidance instructions, a second number of received risk relief instructions, and a sum of the first number of received obstacle avoidance instructions and the second number of received risk relief instructions; and in response to determining that the number of jump instructions is greater than or equal to a predetermined jump threshold, controlling the vehicle to return to an original lane, and cancelling lane changing, wherein the predetermined jump threshold refers to a maximum number of received jump instructions.

6 . The method according to claim 1 , wherein the controlling the vehicle to travel according to the obstacle avoidance strategy in lane changing comprises:
determining a lateral acceleration and a longitudinal acceleration according to the obstacle avoidance strategy in lane changing; and controlling the vehicle to travel according to the lateral acceleration and the longitudinal acceleration.

7 . The method according to claim 1 , further comprising: before the controlling the vehicle to travel according to the obstacle avoidance strategy in lane changing,
acquiring the first obstacle data of the target obstacle and the first vehicle data of the vehicle; determining the first relationship between the target obstacle and the vehicle, based on the first obstacle data of the target obstacle and the first vehicle data of the vehicle; and generating the obstacle avoidance instruction in response to determining that the first relationship between the target obstacle and the vehicle meets the predetermined collision condition.

8 . An electronic device, comprising:
at least one processor; and a memory communicatively connected to the at least one processor, wherein the memory stores instructions executable by the at least one processor, and the instructions, when executed by the at least one processor, are configured to cause the at least one processor to at least: acquire scene data for lane changing about surroundings of a vehicle in response to a lane-changing instruction being received; determine a lane-changing entrance based on the scene data for lane changing; generate a planned path for lane changing based on a travelling location of the vehicle and the lane-changing entrance; determine, in response to an obstacle avoidance instruction being received, an obstacle avoidance strategy in lane changing according to first obstacle data of a target obstacle in a process of controlling the vehicle to change lanes according to the planned path for lane changing, wherein the obstacle avoidance instruction is generated in response to determining that a first relationship between the target obstacle and the vehicle meets a predetermined collision condition, the first relationship between the target obstacle and the vehicle is generated based on the first obstacle data of the target obstacle and first vehicle data of the vehicle, and the obstacle avoidance strategy in lane changing refers to changing a travelling state of the vehicle while maintaining a lane change; control the vehicle to travel according to the obstacle avoidance strategy in lane changing; and update a planned path for lane changing in response to a risk relief instruction being received, so that the vehicle travels according to the updated planned path for lane changing, wherein the risk relief instruction is generated in response to determining that a second relationship between the target obstacle and the vehicle does not meet the predetermined collision condition,

Assignees

• Apollo Intelligent Driving Technology Beijing Co Ltd

Inventors

• Yang Huangrong
• Xie Mengqi
• Ma Lin
• Xia Zhongpu

Classifications

• B60W30/18163 Primary

  Lane change; Overtaking manoeuvres · CPC title

• B60W30/0956 Primary

  the prediction being responsive to traffic or environmental parameters · CPC title

• B60W30/0953

  the prediction being responsive to vehicle dynamic parameters · CPC title

• B60W2554/80

  Spatial relation or speed relative to objects · CPC title

• B60W2554/4044

  Direction of movement, e.g. backwards · CPC title